从策展媒体中进行弱监督集体特征学习
Weakly supervised collective feature learning from curated media
摘要：
当前特征学习的最新技术依赖于对由目标内容项及其各自的类别标签组成的大规模数据集的监督学习。然而，构建这种大规模的完全标记的数据集通常需要艰苦的手动工作。这个问题的一个可能的解决方案是采用社区贡献的文本标签作为弱标签，然而，单个文本标签背后的概念强烈依赖于用户。相反，我们提出了一个新的范式，通过充分利用人类的社会网络服务（SNS）的策展过程中学习的歧视性功能。在内容策展过程中，SNS用户从各种来源手动收集内容项，并根据上下文对其进行分组，这一切都是为了他们自己的利益。由于该过程的性质，我们可以假设（1）同一组中的内容项共享相同的语义概念，以及（2）共享相同图像的组可能具有相关的语义概念。通过这些见解，我们可以将人类策划的组定义为弱标签，我们提出的框架可以从中学习区分性特征，作为用户在创建组时意图的语义概念空间中的表示。我们表明，这种特征学习可以制定为一个二分图的链接预测的问题，其节点对应于内容项和人类策划的群体，并提出了一种新的方法，基于稀疏编码或网络微调的特征学习。
英文摘要：
The current state-of-the-art in feature learning relies on the supervised learning of large-scale datasets consisting of target content items and their respective category labels. However, constructing such large-scale fully-labeled datasets generally requires painstaking manual effort. One possible solution to this problem is to employ community contributed text tags as weak labels, however, the concepts underlying a single text tag strongly depends on the users. We instead present a new paradigm for learning discriminative features by making full use of the human curation process on social networking services (SNSs). During the process of content curation, SNS users collect content items manually from various sources and group them by context, all for their own benefit. Due to the nature of this process, we can assume that (1) content items in the same group share the same semantic concept and (2) groups sharing the same images might have related semantic concepts. Through these insights, we can define human curated groups as weak labels from which our proposed framework can learn discriminative features as a representation in the space of semantic concepts the users intended when creating the groups. We show that this feature learning can be formulated as a problem of link prediction for a bipartite graph whose nodes corresponds to content items and human curated groups, and propose a novel method for feature learning based on sparse coding or network fine-tuning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
